	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 66.5%	1st 68.0%	6th 50.5%	3rd 64.1%	5th 61.1%	4th 63.1%
62.8%	71%	62%		64%	62%	55%
67.0%	71%	65%		69%	60%	70%
83.8%	84%	87%		88%	78%	82%
77.8%	86%	77%		73%	69%	84%
46.8%	63%	34%		46%	28%	63%
65.0%	60%	64%		67%	62%	72%
69.4%	71%	67%		67%	74%	68%
57.8%	72%	100%		40%	37%	40%
58.8%	61%	68%		57%	47%	61%
64.4%	70%	79%		62%	44%	67%
93.4%	93%	96%		93%	95%	90%
76.8%	79%	63%		80%	85%	77%
59.0%	72%	80%		72%	20%	51%
62.0%	67%	58%		59%	64%	62%
53.8%	60%	49%		55%	56%	49%
64.2%	67%	67%		64%	57%	66%
78.0%	83%	79%		79%	76%	73%
59.0%	57%	82%		55%	54%	47%
32.0%	34%	39%		34%	23%	30%
62.5%	61%	68%	43%	58%	81%	64%
80.4%	79%	84%		75%	89%	75%
82.4%	87%	84%		80%	79%	82%
53.6%	60%	61%		49%	54%	44%
56.8%	62%	67%		59%	54%	42%
66.0%	71%	72%	58%	63%	69%	63%
68.8%	72%	70%		68%	64%	70%
89.8%	89%	94%		90%	85%	91%
47.0%	54%	56%		37%	53%	35%
74.6%	82%	73%		80%	67%	71%
49.6%	50%	58%		43%	39%	58%
64.2%	65%	59%		63%	68%	66%
59.0%	56%	53%		67%	50%	69%
76.4%	70%	80%		69%	86%	77%
75.4%	79%	76%		72%	74%	76%
38.6%	31%	47%		43%	35%	37%
70.6%	55%	79%		74%	76%	69%
65.6%	65%	67%		64%	71%	61%
53.8%	56%	64%		51%	51%	47%
65.0%	60%	66%		73%	63%	63%
58.8%	56%	56%		55%	73%	54%
59.2%	59%	62%		55%	64%	56%
66.4%	67%	72%		62%	67%	64%
65.2%	52%	75%		75%	62%	62%
74.4%	86%	73%		83%	65%	65%
64.8%	63%	62%		66%	65%	68%
56.6%	54%	60%		55%	51%	63%
45.4%	51%	44%		57%	23%	52%
54.8%	61%	62%		43%	62%	46%
56.6%	65%	66%		53%	48%	51%
57.2%	61%	67%		63%	35%	60%
78.2%	85%	77%		72%	77%	80%
67.8%	70%	70%		65%	67%	67%
79.8%	76%	81%		81%	76%	85%
63.4%	60%	52%		74%	65%	66%